{"paper_id":"2503.04873","title":"Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?","authors":["Xinyu Wei","Luojia Liu"],"paper_date":"2025-03-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2503.04873v1","page_url":"https://thequant.space/flowcharts/are-large-language-models-good-in-context-learners-for-finan/","scores":{"empirical_rigor":9,"math_complexity":1,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes to explore in-context learning for financial sentiment analysis using modern large language models.","quote":"To the best of our knowledge, this is the first paper exploring in-context learning for FSA that covers most modern LLMs (recently released DeepSeek V3 included) and multiple in-context sample selection methods.","summary":"Recently, large language models (LLMs) with hundreds of billions of parameters have demonstrated the emergent ability, surpassing traditional methods in various domains even without fine-tuning over domain-specific data. However, when it comes to financial sentiment analysis (FSA)“x2013”a…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The temperature of LLMs is set to 1 for all experiments.","type":"model","stated":"explicit","quote":"The temperature of LLMs is set to 1."},{"assumption":"A default number of shots (6) is used for in‑context learning comparisons.","type":"model","stated":"explicit","quote":"we first compare various in-context learning strategies with a default number of shots as 6 with the zero-shot LLMs."},{"assumption":"Fine‑tuning LLMs on finance‑specific data is difficult or impossible, motivating the use of in‑context learning.","type":"data","stated":"explicit","quote":"given that finetuning these models on finance-specific data is difficult, if not impossible at all."}]},"datasets":{"status":"available","items":[{"name":"FiQA2","provider":null,"kind":"text-news","access":"public","period":null,"universe":null,"quote":"We adopt two real‑world datasets—FiQA2 and Twitter3."},{"name":"Twitter","provider":null,"kind":"text-news","access":"public","period":null,"universe":null,"quote":"We adopt two real‑world datasets—FiQA2 and Twitter3.","known_id":"twitter"}],"known":[{"id":"fiqa","name":"FiQA","provider":"FiQA challenge","kind":"benchmark","access":"public","quote":"FiQA is a financial dataset adapted from WWW’18 open challenge (Maia et al., 2018).","mentions":14,"used_in":1},{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"Twitter contains financial news extracted from the tweets using the Twitter API.","mentions":13,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"In‑context learning methods almost consistently enhance LLM performance for financial sentiment analysis.","kind":"performance","quote":"in‑context learning methods almost consistently enhance the LLMs for FSA, which demonstrates that LLMs are indeed effective in‑context learners for FSA."},{"finding":"Clustering‑based sample selection often outperforms other in‑context learning methods, especially on the Twitter dataset.","kind":"performance","quote":"we find that the clustering‑based selection often outperforms other in‑context learning methods, particularly on the Twitter dataset."},{"finding":"Performance of in‑context learning does not fluctuate much with varying numbers of shots, indicating few demonstrations suffice.","kind":"performance","quote":"we observe that the performance of in‑context learning does not fluctuate a lot when the number of shots varies."},{"finding":"Zero‑shot LLMs often yield the worst performance compared to in‑context methods across multiple models and datasets.","kind":"performance","quote":"the zero‑shot LLM has the worst performance by Gemini 2.0 Flash, Llama 3.1 405B, GPT‑4 Turbo, GPT‑4o mini, and Claude 3.5 Sonnet on FiQA."},{"finding":"In‑context learning improves classification of neutral financial samples, which are the most ambiguous.","kind":"predictive-accuracy","quote":"in‑context learning methods yield better performance on neutral samples, while the results of positive and negative samples do not diminish."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":52,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:43:22Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}